Sumin Kim

Recent advances in segmentation foundation models have enabled accurate and efficient segmentation across a wide range of natural images and videos, but their utility to medical data remains unclear. In this work, we first present a comprehensive benchmarking of the Segment Anything Model 2 (SAM2) across 11 medical image modalities and videos and point out its strengths and weaknesses by comparing it to SAM1 and MedSAM. Then, we develop a transfer learning pipeline and demonstrate SAM2 can be quickly adapted to medical domain by fine-tuning. Furthermore, we implement SAM2 as a 3D slicer plugin and Gradio API for efficient 3D image and video segmentation. The code has been made publicly available at \url{https://github.com/bowang-lab/MedSAM}.

An improved algorithm for fast motion estimation based on the block-matching algorithm is presented for use in a block-based video coding system. To achieve enhanced motion estimation performance, an adaptive search pattern length for each iteration for the current macro-block is proposed. In addition, search points that must be checked are determined by means of directional information from the error surface, thus reducing intermediate searches. The proposed algorithm is tested with several sequences and excellent performance is verified.

As the use of containers has become mainstream in the cloud environment, various security threats targeting containers have also been increasing. Among them, a notable malicious activity is a cryptojacking attack that steals resources without the consent of an instance owner to mine cryptocurrency. However, detecting such anomalies in a containerized environment is more complex because containers share the host kernel, making it challenging to pinpoint resource usage and anomalies at the container granularity without introducing significant overhead. To this end, this study proposes a runtime detection framework for identifying malicious mining behaviors in the cloud-native environment. By leveraging Tetragon, a runtime security tool based on the extended Berkeley Packet Filter (eBPF), we capture system call traces and flow-level information of cryptojacking containers to extract rich feature representations for training and evaluating various machine learning models. As a result of the experiment, our framework delivers up to 99.75% classification accuracy with moderate runtime monitoring overhead.

This paper presents a novel method for reconstructing 3D garment models from a single image of a posed user. Previous studies that have primarily focused on accurately reconstructing garment geometries to match the input garment image may often result in unnatural-looking garments when deformed for new poses. To overcome this limitation, our approach takes a different approach by inferring the fundamental shape of the garment through sewing patterns from a single image, rather than directly reconstructing 3D garments. Our method consists of two stages. Firstly, given a single image of a posed user, it predicts the garment image worn on a T-pose, representing the baseline form of the garment. Then, it estimates the sewing pattern parameters based on the T-pose garment image. By simulating the stitching and draping of the sewing pattern using physics simulation, we can generate 3D garments that can adaptively deform to arbitrary poses. The effectiveness of our method is validated through ablation studies on the major components and a comparison with other approaches.

In the semiconductor industry, a continuous trend of reducing chip size to maintain competitiveness has led to a significant increase in the complexity of the chip design. This paper presents an efficient approach, focusing specifically on the lithography process, known for its potential pattern distortions called lithography hotspots. The methodology proves to be highly effective in detecting lithography hotspots using ResNet50V2 and model soups. To fine-tune the model and address the challenge of class imbalance in the dataset, we introduce data augmentation techniques that rebalance the data while preserving geometric information. The experimental results obtained on the ICCAD-2012 benchmark dataset demonstrate the effectiveness of our proposed methodology. We achieved impressive results, with an average precision of 0.908 and f1 score of 0.926. These outcomes highlight the practical potential of our methodology for applications in the semiconductor industry.